Counting on Big-Bench Hard Counting
91.9Success RateTextGrad
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TextGradsource=Reported, optimizer=GPT-4o-2024-08-06, student model=GPT-3.5-turbo-11062024.06 | 91.9 | — | |
| OptoPrimeimplementation=Trace, optimizer=GPT-4o-2024-08-06, student model=GPT-3.5-turbo-11062024.06 | 89.4 | 55.9 | |
| TextGradversion=24-10-30, optimizer=GPT-4o-2024-08-06, student model=GPT-3.5-turbo-11062024.06 | 89.2 | 142.9 | |
| TextGradimplementation=Trace, optimizer=GPT-4o-2024-08-06, student model=GPT-3.5-turbo-11062024.06 | 87.6 | — |